def assess_atom(atom: Chem.Atom, bt: Chem.BondType) -> Tuple[bool, Chem.BondType]:
if atom.GetAtomicNum() > 8:
return True, bt
elif len(atom.GetNeighbors()) <= 2 and atom.GetIsAromatic():
return True, Chem.BondType.SINGLE
elif len(atom_i.GetNeighbors()) <= 3 and not atom.GetIsAromatic():
return True, bt
else:
return False, bt # too bonded already!
def from_rdkit(cls, rd_atom: Chem.Atom) -> "Atom":
"""
Build a QUBEKit atom from an rdkit atom instance.
"""
atomic_number = rd_atom.GetAtomicNum()
index = rd_atom.GetIdx()
formal_charge = rd_atom.GetFormalCharge()
aromatic = rd_atom.GetIsAromatic()
bonds = [a.GetIdx() for a in rd_atom.GetNeighbors()]
# check for names in the normal places pdb, mol2 and mol
if rd_atom.HasProp("_Name"):
name = rd_atom.GetProp("_Name")
elif rd_atom.HasProp("_TriposAtomName"):
name = rd_atom.GetProp("_TriposAtomName")
else:
try:
name = rd_atom.GetMonomerInfo().GetName().strip()
except AttributeError:
name = None
# stereochem
if rd_atom.HasProp("_CIPCode"):
stereo_code = rd_atom.GetProp("_CIPCode")
else:
stereo_code = None
return cls(
atomic_number=atomic_number,
atom_index=index,
atom_name=name,
formal_charge=formal_charge,
aromatic=aromatic,
stereochemistry=stereo_code,
bonds=bonds,
)
def assess_atom(atom: Chem.Atom, bt: Chem.BondType) -> Tuple[bool, Chem.BondType]:
"""
True means add, False means delete
:param atom:
:param bt:
:return:
"""
n_neigh = sum([self._is_count_valid(neigh) for neigh in atom.GetNeighbors()])
if atom.GetAtomicNum() > 8:
return True, bt
elif atom.HasProp('DELETE'): # if it is to be deleted it should be fine.
return True, bt
elif n_neigh <= 2 and atom.GetIsAromatic():
return True, Chem.BondType.SINGLE
elif n_neigh <= 3 and not atom.GetIsAromatic():
return True, bt
else:
return False, bt # too bonded already!
def get_atom_hybridization(self, atom: Atom):
if self.is_hydrogen(atom):
return self.get_hydrogen_hybridization(atom)
if atom.GetIsAromatic():
return "_R"
if self.has_hybridization(atom):
return "_%s" % self.get_hybridization(atom)
return ""
def atom_features(atom: Chem.Atom):
return np.array(
encoding_onehot_unk(atom.GetSymbol(), [
'C', 'N', 'O', 'S', 'F', 'Si', 'P', 'Cl', 'Br', 'Mg', 'Na', 'Ca',
'Fe', 'As', 'Al', 'I', 'B', 'V', 'K', 'Tl', 'Yb', 'Sb', 'Sn', 'Ag',
'Pd', 'Co', 'Se', 'Ti', 'Zn', 'H', 'Li', 'Ge', 'Cu', 'Au', 'Ni',
'Cd', 'In', 'Mn', 'Zr', 'Cr', 'Pt', 'Hg', 'Pb', 'Unknown'
]) + encoding_onehot(atom.GetDegree(), [0, 1, 2, 3, 4, 5]) +
encoding_onehot_unk(atom.GetTotalNumHs(), [0, 1, 2, 3, 4]) +
encoding_onehot_unk(atom.GetImplicitValence(), [0, 1, 2, 3, 4, 5]) +
[atom.GetIsAromatic()])
def _assess_atom_for_possible_bonding(self, atom: Chem.Atom,
bt: Chem.BondType) -> bool:
"""
Method for add_bond_if_possible
True means add, False means delete
:param atom:
:param bt:
:return:
"""
n_neigh = sum(
[self._is_count_valid(neigh) for neigh in atom.GetNeighbors()])
if atom.GetAtomicNum() > 8:
return True
elif atom.HasProp(
'DELETE'): # if it is to be deleted it should be fine.
return True
elif n_neigh <= 2 and atom.GetIsAromatic():
return True, Chem.BondType.SINGLE
elif n_neigh <= 3 and not atom.GetIsAromatic():
return True
else:
return False # too bonded already!
def atom_to_feat(self, atm: Chem.Atom, owning_mol: Chem.Mol, idx):
# nb the func GetOwningMol could not be used for mol as would return different object each time
this_atms_idx = atm.GetIdx()
assert idx == this_atms_idx
feat = torch.zeros(len(self), dtype=torch.float32)
# One hot encoding of element
try:
feat[self.atms_to_idx[atm.GetSymbol()]] = 1.
except KeyError as ex:
warnings.warn(f"Ignoring the symbol {atm.GetSymbol()}")
idx_up_to = self.number_atom_options
# Atomic Number
feat[idx_up_to] = float(atm.GetAtomicNum())
idx_up_to += 1
# Acceptor/donor
acceptor_ids, donor_ids = self.get_acceptor_and_donor_ids(owning_mol)
# Acceptor
feat[idx_up_to] = float(this_atms_idx in acceptor_ids)
idx_up_to += 1
# Donor
feat[idx_up_to] = float(this_atms_idx in donor_ids)
idx_up_to += 1
# Hybridization
hyb_idx = self.hybridization(atm.GetHybridization())
if hyb_idx is not None:
feat[idx_up_to + hyb_idx] = 1.
idx_up_to += self.number_hyb_options
# Aromatic
feat[idx_up_to] = float(atm.GetIsAromatic())
idx_up_to += 1
# Number of Hydrogens
feat[idx_up_to] = float(atm.GetNumImplicitHs())
idx_up_to += 1
return feat
def atom_to_string(atom: Chem.Atom) -> str:
return '{}|{}|{}|{}|{}|{}|{}|{}|{}|{}|{}|{}|{}|{}'.format(
atom.GetChiralTag(),
atom.GetDegree(),
atom.GetExplicitValence(),
atom.GetFormalCharge(),
atom.GetHybridization(),
atom.GetIsAromatic(),
atom.GetMass(),
atom.GetNumExplicitHs(),
atom.GetNumImplicitHs(),
atom.GetNumRadicalElectrons(),
atom.GetTotalDegree(),
atom.GetTotalNumHs(),
atom.GetTotalValence(),
atom.IsInRing()
)
def atom_feature(atom: Atom) -> Tuple[torch.Tensor, int]:
'''
Extract atom feature vector.
Returns: (feature_vec, feature_dim)
Features:
# item # dim
atomic number 25
exp-valence 7
imp-valence 4
hybridization 7
Hs 5
degree 6
formal charge 6
in ring 1
aromatic 1
mass / 100 1
(sum) 63
'''
index = torch.tensor([
ATOM_MAP[atom.GetAtomicNum()],
atom.GetExplicitValence(),
atom.GetImplicitValence(),
HYBRID_MAP[atom.GetHybridization()],
atom.GetTotalNumHs(),
atom.GetDegree(),
atom.GetFormalCharge() + 2, # -2 ~ 3
int(atom.IsInRing()),
int(atom.GetIsAromatic())
]) + OFFSET
vec = torch.zeros(ATOM_FDIM)
vec[index] = 1.0
vec[-1] = atom.GetMass() / 100
return vec, ATOM_FDIM
def is_aromatic(atom: Atom) -> int:
"""If the atom is aromatic (0 or 1).
"""
return int(atom.GetIsAromatic())